© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110625
    Prev
    Next
    INDEX
    Explanations

    research studies

    np_max-act · gemini-2.0-flash

    This neuron fires on German words and phrases that discuss moral or rule‐based constraints (e.g. “Moral,” “Zensur,” “Regeln,” “in Bezug auf Moral”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     abortion
    -0.07
    Motor
    -0.07
     transmission
    -0.07
    Generated
    -0.06
     Mein
    -0.06
    .")↵↵
    -0.06
     愛
    -0.06
    _while
    -0.06
    Frame
    -0.06
    catch
    -0.06
    POSITIVE LOGITS
    inaire
    0.07
     �
    0.07
    (Environment
    0.06
    ài
    0.06
     maduras
    0.06
    满
    0.06
    ativos
    0.06
    电脑
    0.06
    ilters
    0.06
     ’
    0.06
    Activations Density 0.003%

    No Known Activations